← Discover
GitHub · langchain-ai/open_deep_research↑ +23 today

In-depth research with autonomous artificial intelligence

Developed by LangChain, open-deep-research is an autonomous system that performs multi-step searches on the internet to answer complex questions. It facilitates deep research processes by automating the research process through planning, data collection and synthesis stages.

Updates

  • August 22, 2026: Stars 12,307 → 12,655, repository archived, development stopped.

What you get

  • Multi-step autonomous research for complex questions
  • Compatibility with different model providers and search tools
  • Research processes visualized via LangGraph

Installation

Cloning the repository and preparing the environment
git clone https://github.com/langchain-ai/open_deep_research.git
cd open_deep_research
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
Installing dependencies
uv sync
# or
uv pip install -r pyproject.toml

Running it

Starting the server
# Install dependencies and start the LangGraph server
uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.11 langgraph dev --allow-blocking

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

Conduct an in-depth analysis of [WRITE YOUR RESEARCH TOPIC HERE] using the Open Deep Research tool. Plan your research process, collect data online, and synthesize your findings to create a comprehensive report.

Repository: https://github.com/langchain-ai/open_deep_research. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Artificial Intelligence
Who it is forIt is for developers and researchers who want to automate autonomous research processes on complex topics.
LicenseMIT

Editorial note

Maintenance note: The GitHub source repository is archived. Treat this as an educational reference and verify an active successor/fork for current dependencies and security.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-22: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.